Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.7270. Min Act: -0.1700
Data Index: 1544369 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.6020. Min Act: -0.1700
Data Index: 3743006 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.6020. Min Act: -0.1700
Data Index: 7564185 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.5395. Min Act: -0.1700
Data Index: 5500169 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.5395. Min Act: -0.1700
Data Index: 5386484 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.5082. Min Act: -0.1700
Data Index: 4672853 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.5082. Min Act: -0.1700
Data Index: 901587 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.4457. Min Act: -0.1700
Data Index: 4983628 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.3832. Min Act: -0.1700
Data Index: 8676432 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.3207. Min Act: -0.1700
Data Index: 6765738 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.3207. Min Act: -0.1700
Data Index: 952303 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.3207. Min Act: -0.1700
Data Index: 2718526 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2895. Min Act: -0.1700
Data Index: 487387 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2270. Min Act: -0.1700
Data Index: 1399777 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2270. Min Act: -0.1700
Data Index: 2363328 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2270. Min Act: -0.1700
Data Index: 7137569 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.1957. Min Act: -0.1700
Data Index: 747477 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.1957. Min Act: -0.1700
Data Index: 7419419 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2270. Min Act: -0.1700
Data Index: 5789835 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7270. Min Range: -7.7270
Max Act: 7.2270. Min Act: -0.1700
Data Index: 4020798 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19